multi size, and giant hugetlb page support, 1GB hugetlb for x86

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -22,30 +22,24 @@
 #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 global_hstate;
 
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
 static DEFINE_SPINLOCK(hugetlb_lock);
 
-static void clear_huge_page(struct page *page, unsigned long addr)
+static void clear_huge_page(struct page *page, unsigned long addr, unsigned 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);
 	}

@@ -55,34 +49,35 @@ 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 < 1 << huge_page_order(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;
 		}
 	}

@@ -98,18 +93,19 @@ static struct page *dequeue_huge_page_vm
 	struct zonelist *zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol);
 	struct zone **z;
+	struct hstate *h = hstate_vma(vma);
 
 	for (z = zonelist->zones; *z; z++) {
 		nid = zone_to_nid(*z);
 		if (cpuset_zone_allowed_softwall(*z, 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 (vma && vma->vm_flags & VM_MAYSHARE)
-				resv_huge_pages--;
+				h->resv_huge_pages--;
 			break;
 		}
 	}

@@ -117,23 +113,24 @@ 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 < (1 << huge_page_order(h)); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
 				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
 				1 << PG_private | 1<< PG_writeback);
 	}
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
-	__free_pages(page, HUGETLB_PAGE_ORDER);
+	__free_pages(page, huge_page_order(h));
 }
 
 static void free_huge_page(struct page *page)
 {
+	struct hstate *h = &global_hstate;
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 

@@ -143,12 +140,12 @@ 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)

@@ -160,7 +157,7 @@ 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;

@@ -173,15 +170,15 @@ 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);

@@ -190,18 +187,18 @@ static int adjust_pool_surplus(int delta
 	return ret;
 }
 
-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_NOWARN,
-		HUGETLB_PAGE_ORDER);
+			huge_page_order(h));
 	if (page) {
 		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 */
 	}

@@ -209,17 +206,17 @@ static struct page *alloc_fresh_huge_pag
 	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;
 		/*

@@ -233,17 +230,18 @@ 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);
 
 	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;

@@ -272,17 +270,17 @@ 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_NOWARN,
-					HUGETLB_PAGE_ORDER);
+			   huge_page_order(h));
 
 	spin_lock(&hugetlb_lock);
 	if (page) {

@@ -297,11 +295,11 @@ 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]++;
 	} else {
-		nr_huge_pages--;
-		surplus_huge_pages--;
+		h->nr_huge_pages--;
+		h->surplus_huge_pages--;
 	}
 	spin_unlock(&hugetlb_lock);
 

@@ -312,16 +310,16 @@ 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;
 	}
 

@@ -332,7 +330,7 @@ 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

@@ -353,7 +351,8 @@ 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;
 

@@ -366,13 +365,13 @@ retry:
 	 * before they are reserved.
 	 */
 	needed += allocated;
-	resv_huge_pages += delta;
+	h->resv_huge_pages += delta;
 	ret = 0;
 free:
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 		list_del(&page->lru);
 		if ((--needed) >= 0)
-			enqueue_huge_page(page);
+			enqueue_huge_page(h, page);
 		else {
 			/*
 			 * The page has a reference count of zero already, so

@@ -395,7 +394,8 @@ 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;

@@ -410,27 +410,27 @@ 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();
 		}

@@ -453,16 +453,17 @@ static struct page *alloc_huge_page_priv
 						unsigned long addr)
 {
 	struct page *page = NULL;
+	struct hstate *h = hstate_vma(vma);
 
 	if (hugetlb_get_quota(vma->vm_file->f_mapping, 1))
 		return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
-	if (free_huge_pages > resv_huge_pages)
+	if (h->free_huge_pages > h->resv_huge_pages)
 		page = dequeue_huge_page_vma(vma, addr);
 	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(vma->vm_file->f_mapping, 1);
 			return ERR_PTR(-VM_FAULT_OOM);

@@ -492,21 +493,27 @@ static struct page *alloc_huge_page(stru
 static int __init hugetlb_init(void)
 {
 	unsigned long i;
+	struct hstate *h = &global_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("Total HugeTLB memory allocated, %ld\n", h->free_huge_pages);
 	return 0;
 }
 module_init(hugetlb_init);

@@ -534,19 +541,21 @@ static unsigned int cpuset_mems_nr(unsig
 #ifdef CONFIG_HIGHMEM
 static void try_to_free_low(unsigned long count)
 {
+	struct hstate *h = &global_hstate;
 	int i;
 
 	for (i = 0; i < MAX_NUMNODES; ++i) {
 		struct page *page, *next;
-		list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
+		struct list_head *freel = &h->hugepage_freelists[i];
+		list_for_each_entry_safe(page, next, freel, lru) {
 			if (count >= 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)]--;
 		}
 	}
 }

@@ -556,10 +565,11 @@ static inline void try_to_free_low(unsig
 }
 #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 = &global_hstate;
 
 	/*
 	 * Increase the pool size

@@ -573,12 +583,12 @@ 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)) {
 		int ret;
 		/*
 		 * If this allocation races such that we no longer need the

@@ -586,7 +596,7 @@ static unsigned long set_max_huge_pages(
 		 * 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;

@@ -608,21 +618,21 @@ 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();
+	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;
 }

@@ -652,9 +662,10 @@ int hugetlb_overcommit_handler(struct ct
 			struct file *file, void __user *buffer,
 			size_t *length, loff_t *ppos)
 {
+	struct hstate *h = &global_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;
 }

@@ -663,34 +674,37 @@ int hugetlb_overcommit_handler(struct ct
 
 int hugetlb_report_meminfo(char *buf)
 {
+	struct hstate *h = &global_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 = &global_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 = &global_hstate;
+	return h->nr_huge_pages * (1 << huge_page_order(h));
 }
 
 /*

@@ -745,14 +759,16 @@ int copy_hugetlb_page_range(struct mm_st
 	struct page *ptepage;
 	unsigned long addr;
 	int cow;
+	struct hstate *h = hstate_vma(vma);
+	unsigned 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;
 

@@ -788,6 +804,9 @@ void __unmap_hugepage_range(struct vm_ar
 	pte_t pte;
 	struct page *page;
 	struct page *tmp;
+	struct hstate *h = hstate_vma(vma);
+	unsigned 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

@@ -796,11 +815,11 @@ 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;

@@ -848,6 +867,7 @@ static int hugetlb_cow(struct mm_struct 
 {
 	struct page *old_page, *new_page;
 	int avoidcopy;
+	struct hstate *h = hstate_vma(vma);
 
 	old_page = pte_page(pte);
 

@@ -872,7 +892,7 @@ static int hugetlb_cow(struct mm_struct 
 	__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(*ptep, pte))) {
 		/* Break COW */
 		set_huge_pte_at(mm, address, ptep,

@@ -894,10 +914,11 @@ static int hugetlb_no_page(struct mm_str
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	struct hstate *h = hstate_vma(vma);
 
 	mapping = vma->vm_file->f_mapping;
-	idx = ((address - vma->vm_start) >> HPAGE_SHIFT)
-		+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+	idx = ((address - vma->vm_start) >> huge_page_shift(h))
+		+ (vma->vm_pgoff >> huge_page_order(h));
 
 	/*
 	 * Use page lock to guard against racing truncation

@@ -906,7 +927,7 @@ 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);

@@ -914,7 +935,7 @@ 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) {

@@ -930,14 +951,14 @@ retry:
 			}
 
 			spin_lock(&inode->i_lock);
-			inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+			inode->i_blocks += (huge_page_size(h)) / 512;
 			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;
 

@@ -973,8 +994,9 @@ 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;
 

@@ -1012,6 +1034,7 @@ 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) {

@@ -1023,7 +1046,7 @@ 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 || pte_none(*pte) || (write && !pte_write(*pte))) {
 			int ret;

@@ -1040,7 +1063,7 @@ 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(*pte);
 same_page:
 		if (pages) {

@@ -1056,7 +1079,7 @@ same_page:
 		--remainder;
 		++i;
 		if (vaddr < vma->vm_end && remainder &&
-				pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+				pfn_offset < (1 << huge_page_order(h))) {
 			/*
 			 * We use pfn_offset to avoid touching the pageframes
 			 * of this compound page.

@@ -1078,13 +1101,14 @@ 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;

@@ -1223,7 +1247,7 @@ static long region_truncate(struct list_
 	return chg;
 }
 
-static int hugetlb_acct_memory(long delta)
+static int hugetlb_acct_memory(struct hstate *h, long delta)
 {
 	int ret = -ENOMEM;
 

@@ -1246,18 +1270,18 @@ 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);

@@ -1267,6 +1291,7 @@ out:
 int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 {
 	long ret, chg;
+	struct hstate *h = &global_hstate;
 
 	chg = region_chg(&inode->i_mapping->private_list, from, to);
 	if (chg < 0)

@@ -1274,7 +1299,7 @@ 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;

@@ -1285,12 +1310,13 @@ int hugetlb_reserve_pages(struct inode *
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
+	struct hstate *h = &global_hstate;
 	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 -= ((huge_page_size(h))/512) * freed;
 	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 +128,7 @@ 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, int sz)
 {
 	pgd_t *pg;
 	pud_t *pu;

Index: linux-2.6/arch/sparc64/mm/hugetlbpage.c
===================================================================
@@ -195,7 +195,7 @@ 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, int sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

Index: linux-2.6/arch/sh/mm/hugetlbpage.c
===================================================================
@@ -22,7 +22,7 @@
 #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, int 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, int sz)
 {
 	unsigned long taddr = htlbpage_to_page(addr);
 	pgd_t *pgd;

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -124,7 +124,7 @@ 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, int sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;

91 lines not on this page · raw message

156 lines not on this page · raw message

Index: linux-2.6/ipc/shm.c
===================================================================
@@ -613,7 +613,8 @@ 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 += (1 << huge_page_order(h)) * mapping->nrpages;
 		} else {
 			struct shmem_inode_info *info = SHMEM_I(inode);
 			spin_lock(&info->lock);

Index: linux-2.6/mm/memory.c
===================================================================
@@ -848,7 +848,7 @@ unsigned long unmap_vmas(struct mmu_gath
 			if (unlikely(is_vm_hugetlb_page(vma))) {
 				unmap_hugepage_range(vma, start, end);
 				zap_work -= (end - start) /
-						(HPAGE_SIZE / PAGE_SIZE);
+					(1 << huge_page_order(hstate_vma(vma)));
 				start = end;
 			} else
 				start = unmap_page_range(*tlbp, vma,

Index: linux-2.6/mm/mempolicy.c
===================================================================
@@ -1295,7 +1295,8 @@ struct zonelist *huge_zonelist(struct vm
 	if (pol->policy == MPOL_INTERLEAVE) {
 		unsigned nid;
 
-		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
+		nid = interleave_nid(pol, vma, addr,
+					huge_page_shift(hstate_vma(vma)));
 		if (unlikely(pol != &default_policy &&
 				pol != current->mempolicy))
 			__mpol_free(pol);	/* finished with pol */

@@ -1944,9 +1945,12 @@ static void check_huge_range(struct vm_a
 {
 	unsigned long addr;
 	struct page *page;
+	struct hstate *h = hstate_vma(vma);
+	unsigned 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
===================================================================
@@ -1793,7 +1793,8 @@ 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/mm/hugetlb.c
===================================================================
@@ -27,7 +27,15 @@ unsigned long sysctl_overcommit_huge_pag
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 
-struct hstate global_hstate;
+static int max_hstate = 1;
+
+struct hstate hstates[HUGE_MAX_HSTATE];
+
+/* for command line parsing */
+struct hstate *parsed_hstate __initdata = &global_hstate;
+
+#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

@@ -128,9 +136,19 @@ 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)
 {
-	struct hstate *h = &global_hstate;
+	struct hstate *h = size_to_hstate(PAGE_SIZE << compound_order(page));
 	int nid = page_to_nid(page);
 	struct address_space *mapping;
 

@@ -490,15 +508,11 @@ static struct page *alloc_huge_page(stru
 	return page;
 }
 
-static int __init hugetlb_init(void)
+static int __init hugetlb_init_hstate(struct hstate *h)
 {
 	unsigned long i;
-	struct hstate *h = &global_hstate;
 
-	if (HPAGE_SHIFT == 0)
-		return 0;
-
-	if (!h->order) {
+	if (h == &global_hstate && !h->order) {
 		h->order = HPAGE_SHIFT - PAGE_SHIFT;
 		h->mask = HPAGE_MASK;
 	}

@@ -513,11 +527,35 @@ static int __init hugetlb_init(void)
 			break;
 	}
 	max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
-	printk("Total HugeTLB memory allocated, %ld\n", h->free_huge_pages);
+
+	printk(KERN_INFO "Total HugeTLB memory allocated, %ld %dMB pages\n",
+			h->free_huge_pages,
+			1 << (h->order + PAGE_SHIFT - 20));
 	return 0;
 }
+
+static int __init hugetlb_init(void)
+{
+	if (HPAGE_SHIFT == 0)
+		return 0;
+	return hugetlb_init_hstate(&global_hstate);
+}
 module_init(hugetlb_init);
 
+/* Should be called on processing a hugepagesz=... option */
+void __init huge_add_hstate(unsigned order)
+{
+	struct hstate *h;
+	BUG_ON(size_to_hstate(PAGE_SIZE << order));
+	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
+	BUG_ON(order <= HPAGE_SHIFT - PAGE_SHIFT);
+	h = &hstates[max_hstate++];
+	h->order = order;
+	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
+	hugetlb_init_hstate(h);
+	parsed_hstate = h;
+}
+
 static int __init hugetlb_setup(char *s)
 {
 	if (sscanf(s, "%lu", &max_huge_pages) <= 0)

@@ -539,28 +577,27 @@ 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)
 {
-	struct hstate *h = &global_hstate;
 	int i;
 
 	for (i = 0; i < MAX_NUMNODES; ++i) {
 		struct page *page, *next;
 		struct list_head *freel = &h->hugepage_freelists[i];
 		list_for_each_entry_safe(page, next, freel, lru) {
-			if (count >= nr_huge_pages)
+			if (count >= h->nr_huge_pages)
 				return;
 			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)]--;
 		}
 	}
 }
 #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

@@ -620,7 +657,7 @@ static unsigned long set_max_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);
+	try_to_free_low(h, min_count);
 	while (min_count < persistent_huge_pages(h)) {
 		struct page *page = dequeue_huge_page(h);
 		if (!page)

@@ -1291,7 +1328,7 @@ out:
 int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 {
 	long ret, chg;
-	struct hstate *h = &global_hstate;
+	struct hstate *h = hstate_inode(inode);
 
 	chg = region_chg(&inode->i_mapping->private_list, from, to);
 	if (chg < 0)

@@ -1310,7 +1347,7 @@ int hugetlb_reserve_pages(struct inode *
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
-	struct hstate *h = &global_hstate;
+	struct hstate *h = hstate_inode(inode);
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
 	spin_lock(&inode->i_lock);

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -212,7 +212,16 @@ struct hstate {
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 };
 
-extern struct hstate global_hstate;
+void __init huge_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];
+
+#define global_hstate (hstates[0])
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
 {

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -709,39 +709,59 @@ int hugetlb_overcommit_handler(struct ct
 
 #endif /* CONFIG_SYSCTL */
 
+static int dump_field(char *buf, unsigned field)
+{
+	int n = 0;
+	struct hstate *h;
+	for_each_hstate (h)
+		n += sprintf(buf + n, " %5lu", *(unsigned long *)((char *)h + field));
+	buf[n++] = '\n';
+	return n;
+}
+
 int hugetlb_report_meminfo(char *buf)
 {
-	struct hstate *h = &global_hstate;
-	return sprintf(buf,
-			"HugePages_Total: %5lu\n"
-			"HugePages_Free:  %5lu\n"
-			"HugePages_Rsvd:  %5lu\n"
-			"HugePages_Surp:  %5lu\n"
-			"Hugepagesize:    %5lu kB\n",
-			h->nr_huge_pages,
-			h->free_huge_pages,
-			h->resv_huge_pages,
-			h->surplus_huge_pages,
-			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
+	struct hstate *h;
+	int n = 0;
+	n += sprintf(buf + 0, "HugePages_Total:");
+	n += dump_field(buf + n, offsetof(struct hstate, nr_huge_pages));
+	n += sprintf(buf + n, "HugePages_Free: ");
+	n += dump_field(buf + n, offsetof(struct hstate, free_huge_pages));
+	n += sprintf(buf + n, "HugePages_Rsvd: ");
+	n += dump_field(buf + n, offsetof(struct hstate, resv_huge_pages));
+	n += sprintf(buf + n, "HugePages_Surp: ");
+	n += dump_field(buf + n, offsetof(struct hstate, surplus_huge_pages));
+	n += sprintf(buf + n, "Hugepagesize:   ");
+	for_each_hstate (h)
+		n += sprintf(buf + n, " %5u", huge_page_size(h) / 1024);
+	n += sprintf(buf + n, " kB\n");
+	return n;
 }
 
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
-	struct hstate *h = &global_hstate;
-	return sprintf(buf,
-		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n"
-		"Node %d HugePages_Surp:  %5u\n",
-		nid, h->nr_huge_pages_node[nid],
-		nid, h->free_huge_pages_node[nid],
-		nid, h->surplus_huge_pages_node[nid]);
+	int n = 0;
+	n += sprintf(buf, "Node %d HugePages_Total: ", nid);
+	n += dump_field(buf + n, offsetof(struct hstate,
+						nr_huge_pages_node[nid]));
+	n += sprintf(buf + n, "Node %d HugePages_Free: ", nid);
+	n += dump_field(buf + n, offsetof(struct hstate,
+						free_huge_pages_node[nid]));
+	n += sprintf(buf + n, "Node %d HugePages_Surp: ", nid);
+	n += dump_field(buf + n, offsetof(struct hstate,
+						surplus_huge_pages_node[nid]));
+	return n;
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &global_hstate;
-	return h->nr_huge_pages * (1 << huge_page_order(h));
+	long x = 0;
+	struct hstate *h;
+	for_each_hstate (h) {
+		x += h->nr_huge_pages * (1 << huge_page_order(h));
+	}
+	return x;
 }
 
 /*

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -136,6 +136,7 @@ struct hugetlbfs_config {
 	umode_t mode;
 	long	nr_blocks;
 	long	nr_inodes;
+	struct hstate *hstate;
 };
 
 struct hugetlbfs_sb_info {

@@ -144,6 +145,7 @@ struct hugetlbfs_sb_info {
 	long	max_inodes;   /* inodes allowed */
 	long	free_inodes;  /* inodes free */
 	spinlock_t	stat_lock;
+	struct hstate *hstate;
 };
 
 

@@ -223,19 +225,21 @@ extern struct hstate hstates[HUGE_MAX_HS
 
 #define global_hstate (hstates[0])
 
-static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
+static inline struct hstate *hstate_inode(struct inode *i)
 {
-	return &global_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 &global_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 &global_hstate;
+	return hstate_file(vma->vm_file);
 }
 
 static inline unsigned huge_page_size(struct hstate *h)

112 lines not on this page · raw message

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -904,19 +904,9 @@ void __unmap_hugepage_range(struct vm_ar
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			  unsigned long end)
 {
-	/*
-	 * 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);
-		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);
+	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 }
 
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,

Index: linux-2.6/mm/memory.c
===================================================================
@@ -846,9 +846,23 @@ unsigned long unmap_vmas(struct mmu_gath
 			}
 
 			if (unlikely(is_vm_hugetlb_page(vma))) {
-				unmap_hugepage_range(vma, start, end);
-				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);
+					zap_work -= (end - start) /
 					(1 << huge_page_order(hstate_vma(vma)));
+				}
+
 				start = end;
 			} else
 				start = unmap_page_range(*tlbp, vma,

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -32,8 +32,6 @@ int hugetlb_fault(struct mm_struct *mm, 
 int hugetlb_reserve_pages(struct inode *inode, long from, long to);
 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;

@@ -262,6 +260,9 @@ static inline unsigned huge_page_shift(s
 	return h->order + PAGE_SHIFT;
 }
 
+extern unsigned long max_huge_pages[HUGE_MAX_HSTATE];
+extern unsigned long sysctl_overcommit_huge_pages[HUGE_MAX_HSTATE];
+
 #else
 struct hstate {};
 #define hstate_file(f) NULL

Index: linux-2.6/kernel/sysctl.c
===================================================================
@@ -935,7 +935,7 @@ static struct ctl_table vm_table[] = {
 	 {
 		.procname	= "nr_hugepages",
 		.data		= &max_huge_pages,
-		.maxlen		= sizeof(unsigned long),
+		.maxlen 	= sizeof(max_huge_pages),
 		.mode		= 0644,
 		.proc_handler	= &hugetlb_sysctl_handler,
 		.extra1		= (void *)&hugetlb_zero,

86 lines not on this page · raw message

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -224,6 +224,27 @@ 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;

@@ -237,21 +258,7 @@ 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);
 
 	return ret;

Index: linux-2.6/mm/bootmem.c
===================================================================
@@ -484,6 +484,18 @@ void * __init __alloc_bootmem_node(pg_da
 	return __alloc_bootmem(size, align, goal);
 }
 
+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
===================================================================
@@ -90,6 +90,10 @@ 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
===================================================================
@@ -13,6 +13,8 @@
 
 #include <linux/mm.h>
 
+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
===================================================================
@@ -272,7 +272,7 @@ 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
===================================================================
@@ -205,6 +205,17 @@ static int adjust_pool_surplus(struct hs
 	return ret;
 }
 
+static void huge_new_page(struct hstate *h, struct page *page)
+{
+	unsigned nid = pfn_to_nid(page_to_pfn(page));
+	set_compound_page_dtor(page, free_huge_page);
+	spin_lock(&hugetlb_lock);
+	h->nr_huge_pages++;
+	h->nr_huge_pages_node[nid]++;
+	spin_unlock(&hugetlb_lock);
+	put_page(page); /* free it into the hugepage allocator */
+}
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;

@@ -212,14 +223,8 @@ static struct page *alloc_fresh_huge_pag
 	page = alloc_pages_node(nid,
 		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
 			huge_page_order(h));
-	if (page) {
-		set_compound_page_dtor(page, free_huge_page);
-		spin_lock(&hugetlb_lock);
-		h->nr_huge_pages++;
-		h->nr_huge_pages_node[nid]++;
-		spin_unlock(&hugetlb_lock);
-		put_page(page); /* free it into the hugepage allocator */
-	}
+	if (page)
+		huge_new_page(h, page);
 
 	return page;
 }

Index: linux-2.6/mm/bootmem.c
===================================================================
@@ -206,8 +206,9 @@ void * __init
 __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	      unsigned long align, unsigned long goal, unsigned long limit)
 {
-	unsigned long offset, remaining_size, areasize, preferred;
-	unsigned long i, start = 0, incr, eidx, end_pfn;
+	unsigned long remaining_size, areasize, preferred;
+	unsigned long i, start, incr, eidx, end_pfn;
+	unsigned long pfn;
 	void *ret;
 
 	if (!size) {

@@ -229,10 +230,6 @@ __alloc_bootmem_core(struct bootmem_data
 		end_pfn = limit;
 
 	eidx = end_pfn - PFN_DOWN(bdata->node_boot_start);
-	offset = 0;
-	if (align && (bdata->node_boot_start & (align - 1UL)) != 0)
-		offset = align - (bdata->node_boot_start & (align - 1UL));
-	offset = PFN_DOWN(offset);
 
 	/*
 	 * We try to allocate bootmem pages above 'goal'

@@ -247,15 +244,18 @@ __alloc_bootmem_core(struct bootmem_data
 	} else
 		preferred = 0;
 
-	preferred = PFN_DOWN(ALIGN(preferred, align)) + offset;
+	start = bdata->node_boot_start;
+	preferred = PFN_DOWN(ALIGN(preferred + start, align) - start);
 	areasize = (size + PAGE_SIZE-1) / PAGE_SIZE;
 	incr = align >> PAGE_SHIFT ? : 1;
+	pfn = PFN_DOWN(start);
+	start = 0;
 
 restart_scan:
 	for (i = preferred; i < eidx; i += incr) {
 		unsigned long j;
 		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
-		i = ALIGN(i, incr);
+		i = ALIGN(pfn + i, incr) - pfn;
 		if (i >= eidx)
 			break;
 		if (test_bit(i, bdata->node_bootmem_map))

@@ -269,11 +269,11 @@ restart_scan:
 		start = i;
 		goto found;
 	fail_block:
-		i = ALIGN(j, incr);
+		i = ALIGN(j + pfn, incr) - pfn;
 	}
 
-	if (preferred > offset) {
-		preferred = offset;
+	if (preferred > 0) {
+		preferred = 0;
 		goto restart_scan;
 	}
 	return NULL;

@@ -289,7 +289,7 @@ found:
 	 */
 	if (align < PAGE_SIZE &&
 	    bdata->last_offset && bdata->last_pos+1 == start) {
-		offset = ALIGN(bdata->last_offset, align);
+		unsigned long offset = ALIGN(bdata->last_offset, align);
 		BUG_ON(offset > PAGE_SIZE);
 		remaining_size = PAGE_SIZE - offset;
 		if (size < remaining_size) {

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

@@ -158,7 +159,7 @@ 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] && h->order <= MAX_ORDER) {
 		update_and_free_page(h, page);
 		h->surplus_huge_pages--;
 		h->surplus_huge_pages_node[nid]--;

@@ -220,6 +221,9 @@ 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_NOWARN,
 			huge_page_order(h));

@@ -276,6 +280,9 @@ 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

@@ -442,6 +449,10 @@ 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) {

@@ -520,6 +531,44 @@ static struct page *alloc_huge_page(stru
 	return page;
 }
 
+static __initdata LIST_HEAD(huge_boot_pages);
+
+struct huge_bm_page {
+	struct list_head list;
+	struct hstate *hstate;
+};
+
+static int __init alloc_bm_huge_page(struct hstate *h)
+{
+	struct huge_bm_page *m;
+	m = __alloc_bootmem_node_nopanic(NODE_DATA(h->hugetlb_next_nid),
+					huge_page_size(h), huge_page_size(h),
+					0);
+	if (!m)
+		return 0;
+	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;
+	hstate_next_node(h);
+	return 1;
+}
+
+/* Put bootmem huge pages into the standard lists after mem_map is up */
+static int __init huge_init_bm(void)
+{
+	struct huge_bm_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);
+		prep_compound_page(page, h->order);
+		huge_new_page(h, page);
+	}
+	return 0;
+}
+__initcall(huge_init_bm);
+
 static int __init hugetlb_init_hstate(struct hstate *h)
 {
 	unsigned long i;

@@ -535,7 +584,10 @@ static int __init hugetlb_init_hstate(st
 	h->hugetlb_next_nid = first_node(node_online_map);
 
 	for (i = 0; i < max_huge_pages[h - hstates]; ++i) {
-		if (!alloc_fresh_huge_page(h))
+		if (h->order > MAX_ORDER) {
+			if (!alloc_bm_huge_page(h))
+				break;
+		} else if (!alloc_fresh_huge_page(h))
 			break;
 	}
 	max_huge_pages[h - hstates] = h->free_huge_pages = h->nr_huge_pages = i;

@@ -594,6 +646,9 @@ 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];

@@ -623,6 +678,11 @@ set_max_huge_pages(struct hstate *h, uns
 
 	*err = 0;
 
+	if (h->order > MAX_ORDER) {
+		*err = -EINVAL;
+		return max_huge_pages[h - hstates];
+	}
+
 	/*
 	 * Increase the pool size
 	 * First take pages out of surplus state.  Then make up the

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -578,19 +578,23 @@ static int __init hugetlb_init_hstate(st
 		h->mask = HPAGE_MASK;
 	}
 
-	for (i = 0; i < MAX_NUMNODES; ++i)
-		INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+	/* Don't reinitialize lists if they have been already init'ed */
+	if (!h->hugepage_freelists[0].next) {
+		for (i = 0; i < MAX_NUMNODES; ++i)
+			INIT_LIST_HEAD(&h->hugepage_freelists[i]);
 
-	h->hugetlb_next_nid = first_node(node_online_map);
+		h->hugetlb_next_nid = first_node(node_online_map);
+	}
 
-	for (i = 0; i < max_huge_pages[h - hstates]; ++i) {
+	while (h->parsed_hugepages < max_huge_pages[h - hstates]) {
 		if (h->order > MAX_ORDER) {
 			if (!alloc_bm_huge_page(h))
 				break;
 		} else if (!alloc_fresh_huge_page(h))
 			break;
+		h->parsed_hugepages++;
 	}
-	max_huge_pages[h - hstates] = h->free_huge_pages = h->nr_huge_pages = i;
+	max_huge_pages[h - hstates] = h->parsed_hugepages;
 
 	printk(KERN_INFO "Total HugeTLB memory allocated, %ld %dMB pages\n",
 			h->free_huge_pages,

@@ -625,6 +629,15 @@ static int __init hugetlb_setup(char *s)
 	unsigned long *mhp = &max_huge_pages[parsed_hstate - hstates];
 	if (sscanf(s, "%lu", mhp) <= 0)
 		*mhp = 0;
+	/*
+	 * Global state is always initialized later in hugetlb_init.
+	 * But we need to allocate > MAX_ORDER hstates here early to still
+	 * use the bootmem allocator.
+	 * If you add additional hstates <= MAX_ORDER you'll need
+	 * to fix that.
+	 */
+	if (parsed_hstate != &global_hstate)
+		hugetlb_init_hstate(parsed_hstate);
 	return 1;
 }
 __setup("hugepages=", hugetlb_setup);

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -210,6 +210,7 @@ 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];
+	unsigned long parsed_hugepages;
 };
 
 void __init huge_add_hstate(unsigned order);

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -531,6 +531,15 @@ static struct page *alloc_huge_page(stru
 	return page;
 }
 
+static __init char *memfmt(char *buf, unsigned long n)
+{
+	if (n >= (1UL << 30))
+		sprintf(buf, "%lu GB", n >> 30);
+	else
+		sprintf(buf, "%lu MB", n >> 20);
+	return buf;
+}
+
 static __initdata LIST_HEAD(huge_boot_pages);
 
 struct huge_bm_page {

@@ -557,14 +566,28 @@ static int __init alloc_bm_huge_page(str
 /* Put bootmem huge pages into the standard lists after mem_map is up */
 static int __init huge_init_bm(void)
 {
+	unsigned long pages = 0;
 	struct huge_bm_page *m;
+	struct hstate *h = NULL;
+	char buf[32];
+
 	list_for_each_entry (m, &huge_boot_pages, list) {
 		struct page *page = virt_to_page(m);
-		struct hstate *h = m->hstate;
+		h = m->hstate;
 		__ClearPageReserved(page);
 		prep_compound_page(page, h->order);
 		huge_new_page(h, page);
+		pages++;
 	}
+
+	/*
+	 * This only prints for a single hstate. This works for x86-64,
+	 * but if you do multiple > MAX_ORDER hstates you'll need to fix it.
+	 */
+	if (pages > 0)
+		printk(KERN_INFO "HugeTLB pre-allocated %ld %s pages\n",
+				h->free_huge_pages,
+				memfmt(buf, huge_page_size(h)));
 	return 0;
 }
 __initcall(huge_init_bm);

@@ -572,6 +595,8 @@ __initcall(huge_init_bm);
 static int __init hugetlb_init_hstate(struct hstate *h)
 {
 	unsigned long i;
+	char buf[32];
+	unsigned long pages = 0;
 
 	if (h == &global_hstate && !h->order) {
 		h->order = HPAGE_SHIFT - PAGE_SHIFT;

@@ -593,12 +618,14 @@ static int __init hugetlb_init_hstate(st
 		} else if (!alloc_fresh_huge_page(h))
 			break;
 		h->parsed_hugepages++;
+		pages++;
 	}
 	max_huge_pages[h - hstates] = h->parsed_hugepages;
 
-	printk(KERN_INFO "Total HugeTLB memory allocated, %ld %dMB pages\n",
+	if (pages > 0)
+		printk(KERN_INFO "HugeTLB pre-allocated %ld %s pages\n",
 			h->free_huge_pages,
-			1 << (h->order + PAGE_SHIFT - 20));
+			memfmt(buf, huge_page_size(h)));
 	return 0;
 }
 

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -45,7 +45,10 @@ struct page *follow_huge_addr(struct mm_
 			      int write);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 				pmd_t *pmd, int write);
+struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
+				pud_t *pud, int write);
 int pmd_huge(pmd_t pmd);
+int pud_huge(pud_t pmd);
 void hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 

@@ -112,8 +115,10 @@ static inline unsigned long hugetlb_tota
 #define hugetlb_report_meminfo(buf)		0
 #define hugetlb_report_node_meminfo(n, buf)	0
 #define follow_huge_pmd(mm, addr, pmd, write)	NULL
+#define follow_huge_pud(mm, addr, pud, write)	NULL
 #define prepare_hugepage_range(addr,len)	(-EINVAL)
 #define pmd_huge(x)	0
+#define pud_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, write)	({ BUG(); 0; })

Index: linux-2.6/arch/ia64/mm/hugetlbpage.c
===================================================================
@@ -106,6 +106,12 @@ int pmd_huge(pmd_t pmd)
 {
 	return 0;
 }
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {

Index: linux-2.6/arch/powerpc/mm/hugetlbpage.c
===================================================================
@@ -368,6 +368,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)

Index: linux-2.6/arch/sh/mm/hugetlbpage.c
===================================================================
@@ -78,6 +78,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {

Index: linux-2.6/arch/sparc64/mm/hugetlbpage.c
===================================================================
@@ -294,6 +294,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -188,6 +188,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)

@@ -208,6 +213,11 @@ int pmd_huge(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PSE);
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)

@@ -216,9 +226,22 @@ follow_huge_pmd(struct mm_struct *mm, un
 
 	page = pte_page(*(pte_t *)pmd);
 	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
 	return page;
 }
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pud);
+	if (page)
+		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
 #endif
 
 /* x86_64 also uses this file */

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -1204,6 +1204,15 @@ int hugetlb_fault(struct mm_struct *mm, 
 	return ret;
 }
 
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+	       pud_t *pud, int write)
+{
+	BUG();
+	return NULL;
+}
+
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			struct page **pages, struct vm_area_struct **vmas,
 			unsigned long *position, int *length, int i,

Index: linux-2.6/mm/memory.c
===================================================================
@@ -945,7 +945,13 @@ struct page *follow_page(struct vm_area_
 	pud = pud_offset(pgd, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
 		goto no_page_table;
-	
+
+	if (pud_huge(*pud)) {
+		BUG_ON(flags & FOLL_GET);
+		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
+		goto out;
+	}
+
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto no_page_table;

@@ -1436,6 +1442,8 @@ static int apply_to_pmd_range(struct mm_
 	unsigned long next;
 	int err;
 
+	BUG_ON(pud_huge(*pud));
+
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -133,9 +133,14 @@ pte_t *huge_pte_alloc(struct mm_struct *
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
-		if (pud_none(*pud))
-			huge_pmd_share(mm, addr, pud);
-		pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		if (sz == PUD_SIZE) {
+			pte = (pte_t *)pud;
+		} else {
+			BUG_ON(sz != PMD_SIZE);
+			if (pud_none(*pud))
+				huge_pmd_share(mm, addr, pud);
+			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 

@@ -151,8 +156,11 @@ pte_t *huge_pte_offset(struct mm_struct 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_present(*pgd)) {
 		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
+		if (pud_present(*pud)) {
+			if (pud_large(*pud))
+				return (pte_t *)pud;
 			pmd = pmd_offset(pud, addr);
+		}
 	}
 	return (pte_t *) pmd;
 }

@@ -215,7 +223,7 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
-	return 0;
+	return !!(pud_val(pud) & _PAGE_PSE);
 }
 
 struct page *

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -421,3 +421,20 @@ hugetlb_get_unmapped_area(struct file *f
 
 #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
 
+#ifdef CONFIG_X86_64
+static __init int setup_hugepagesz(char *opt)
+{
+	unsigned long ps = memparse(opt, &opt);
+	if (ps == PMD_SIZE) {
+		huge_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+	} else if (ps == PUD_SIZE && cpu_has_gbpages) {
+		huge_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else {
+		printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
+			ps >> 20);
+		return 0;
+	}
+	return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif

Index: linux-2.6/include/asm-x86/page.h
===================================================================
@@ -21,6 +21,8 @@
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 
+#define HUGE_MAX_HSTATE 2
+
 /* to align the pointer to the (next) page boundary */
 #define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)
 

Index: linux-2.6/mm/hugetlb.c
===================================================================
@@ -28,12 +28,13 @@ unsigned long sysctl_overcommit_huge_pag
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 
-static int max_hstate = 1;
+static int max_hstate = 0;
 
+static unsigned long default_hstate_resv = 0;
 struct hstate hstates[HUGE_MAX_HSTATE];
 
 /* for command line parsing */
-struct hstate *parsed_hstate __initdata = &global_hstate;
+struct hstate *parsed_hstate __initdata = NULL;
 
 #define for_each_hstate(h) \
 	for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)

@@ -550,58 +551,48 @@ struct huge_bm_page {
 static int __init alloc_bm_huge_page(struct hstate *h)
 {
 	struct huge_bm_page *m;
-	m = __alloc_bootmem_node_nopanic(NODE_DATA(h->hugetlb_next_nid),
+	int nr_nodes = nodes_weight(node_online_map);
+
+	while (nr_nodes) {
+		m = __alloc_bootmem_node_nopanic(NODE_DATA(h->hugetlb_next_nid),
 					huge_page_size(h), huge_page_size(h),
 					0);
-	if (!m)
-		return 0;
+		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;
-	hstate_next_node(h);
 	return 1;
 }
 
 /* Put bootmem huge pages into the standard lists after mem_map is up */
-static int __init huge_init_bm(void)
+static void gather_bootmem_prealloc(void)
 {
 	unsigned long pages = 0;
 	struct huge_bm_page *m;
 	struct hstate *h = NULL;
-	char buf[32];
 
 	list_for_each_entry (m, &huge_boot_pages, list) {
 		struct page *page = virt_to_page(m);
 		h = m->hstate;
 		__ClearPageReserved(page);
+		WARN_ON(page_count(page) != 1);
 		prep_compound_page(page, h->order);
 		huge_new_page(h, page);
 		pages++;
 	}
-
-	/*
-	 * This only prints for a single hstate. This works for x86-64,
-	 * but if you do multiple > MAX_ORDER hstates you'll need to fix it.
-	 */
-	if (pages > 0)
-		printk(KERN_INFO "HugeTLB pre-allocated %ld %s pages\n",
-				h->free_huge_pages,
-				memfmt(buf, huge_page_size(h)));
-	return 0;
 }
-__initcall(huge_init_bm);
 
-static int __init hugetlb_init_hstate(struct hstate *h)
+static void __init hugetlb_init_hstate(struct hstate *h)
 {
 	unsigned long i;
-	char buf[32];
-	unsigned long pages = 0;
-
-	if (h == &global_hstate && !h->order) {
-		h->order = HPAGE_SHIFT - PAGE_SHIFT;
-		h->mask = HPAGE_MASK;
-	}
 
 	/* Don't reinitialize lists if they have been already init'ed */
 	if (!h->hugepage_freelists[0].next) {

@@ -611,29 +602,57 @@ static int __init hugetlb_init_hstate(st
 		h->hugetlb_next_nid = first_node(node_online_map);
 	}
 
-	while (h->parsed_hugepages < max_huge_pages[h - hstates]) {
+	while (h->parsed_hugepages < h->max_huge_pages) {
 		if (h->order > MAX_ORDER) {
 			if (!alloc_bm_huge_page(h))
 				break;
 		} else if (!alloc_fresh_huge_page(h))
 			break;
 		h->parsed_hugepages++;
-		pages++;
 	}
-	max_huge_pages[h - hstates] = h->parsed_hugepages;
+	h->max_huge_pages = h->parsed_hugepages;
+}
 
-	if (pages > 0)
-		printk(KERN_INFO "HugeTLB pre-allocated %ld %s pages\n",
-			h->free_huge_pages,
-			memfmt(buf, huge_page_size(h)));
-	return 0;
+static void __init hugetlb_init_hstates(void)
+{
+	struct hstate *h;
+
+	for_each_hstate (h) {
+		/* oversize hugepages were init'ed in early boot */
+		if (h->order <= MAX_ORDER)
+			hugetlb_init_hstate(h);
+		max_huge_pages[h - hstates] = h->max_huge_pages;
+	}
+}
+
+static void __init report_hugepages(void)
+{
+	struct hstate *h;
+
+	for_each_hstate (h) {
+		char buf[32];
+		printk(KERN_INFO "HugeTLB registered size %s, pre-allocated %ld pages\n",
+				memfmt(buf, huge_page_size(h)),
+				h->free_huge_pages);
+	}
 }
 
 static int __init hugetlb_init(void)
 {
-	if (HPAGE_SHIFT == 0)
-		return 0;
-	return hugetlb_init_hstate(&global_hstate);
+	BUILD_BUG_ON(HPAGE_SHIFT == 0);
+
+	if (!size_to_hstate(HPAGE_SIZE)) {
+		huge_add_hstate(HUGETLB_PAGE_ORDER);
+		parsed_hstate->max_huge_pages = default_hstate_resv;
+	}
+
+	hugetlb_init_hstates();
+
+	gather_bootmem_prealloc();
+
+	report_hugepages();
+
+	return 0;
 }
 module_init(hugetlb_init);
 

@@ -641,9 +660,14 @@ module_init(hugetlb_init);
 void __init huge_add_hstate(unsigned order)
 {
 	struct hstate *h;
-	BUG_ON(size_to_hstate(PAGE_SIZE << order));
+
+	if (size_to_hstate(PAGE_SIZE << order)) {
+		printk("hugepagesz= specified twice, ignoring\n");
+		return;
+	}
+
 	BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
-	BUG_ON(order <= HPAGE_SHIFT - PAGE_SHIFT);
+	BUG_ON(order < HPAGE_SHIFT - PAGE_SHIFT);
 	h = &hstates[max_hstate++];
 	h->order = order;
 	h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);

@@ -653,17 +677,22 @@ void __init huge_add_hstate(unsigned ord
 
 static int __init hugetlb_setup(char *s)
 {
-	unsigned long *mhp = &max_huge_pages[parsed_hstate - hstates];
+	unsigned long *mhp;
+
+	if (!max_hstate)
+		mhp = &default_hstate_resv;
+	else
+		mhp = &parsed_hstate->max_huge_pages;
+
 	if (sscanf(s, "%lu", mhp) <= 0)
 		*mhp = 0;
+
 	/*
 	 * Global state is always initialized later in hugetlb_init.
 	 * But we need to allocate > MAX_ORDER hstates here early to still
 	 * use the bootmem allocator.
-	 * If you add additional hstates <= MAX_ORDER you'll need
-	 * to fix that.
 	 */
-	if (parsed_hstate != &global_hstate)
+	if (max_hstate > 0 && parsed_hstate->order > MAX_ORDER)
 		hugetlb_init_hstate(parsed_hstate);
 	return 1;
 }

@@ -719,8 +748,9 @@ set_max_huge_pages(struct hstate *h, uns
 	*err = 0;
 
 	if (h->order > MAX_ORDER) {
-		*err = -EINVAL;
-		return max_huge_pages[h - hstates];
+		if (count != h->max_huge_pages)
+			*err = -EINVAL;
+		return h->max_huge_pages;
 	}
 
 	/*

@@ -795,19 +825,24 @@ int hugetlb_sysctl_handler(struct ctl_ta
 {
 	int err = 0;
 	struct hstate *h;
-	int i;
+
 	err = proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
 	if (err)
 		return err;
-	i = 0;
-	for_each_hstate (h) {
-		max_huge_pages[i] = set_max_huge_pages(h, max_huge_pages[i],
-							&err);
-		if (err)
-			return err;
-		i++;
+
+	if (write) {
+		for_each_hstate (h) {
+			int tmp;
+
+			h->max_huge_pages = set_max_huge_pages(h,
+					max_huge_pages[h - hstates], &tmp);
+			max_huge_pages[h - hstates] = h->max_huge_pages;
+			if (tmp && !err)
+				err = tmp;
+		}
 	}
-	return 0;
+
+	return err;
 }
 
 int hugetlb_treat_movable_handler(struct ctl_table *table, int write,

Index: linux-2.6/fs/hugetlbfs/inode.c
===================================================================
@@ -827,7 +827,7 @@ hugetlbfs_parse_options(char *options, s
 		struct hstate *h = pconfig->hstate;
 		if (setsize == SIZE_PERCENT) {
 			size <<= huge_page_shift(h);
-			size *= max_huge_pages[h - hstates];
+			size *= h->max_huge_pages;
 			do_div(size, 100);
 		}
 		pconfig->nr_blocks = (size >> huge_page_shift(h));

@@ -857,7 +857,7 @@ hugetlbfs_fill_super(struct super_block 
 	config.uid = current->fsuid;
 	config.gid = current->fsgid;
 	config.mode = 0755;
-	config.hstate = &global_hstate;
+	config.hstate = size_to_hstate(HPAGE_SIZE);
 	ret = hugetlbfs_parse_options(data, &config);
 	if (ret)
 		return ret;

Index: linux-2.6/include/linux/hugetlb.h
===================================================================
@@ -208,7 +208,10 @@ struct hstate {
 	int hugetlb_next_nid;
 	unsigned int order;
 	unsigned long mask;
-	unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
+	unsigned long max_huge_pages;
+	unsigned long nr_huge_pages;
+	unsigned long free_huge_pages;
+	unsigned long resv_huge_pages;
 	unsigned long surplus_huge_pages;
 	unsigned long nr_overcommit_huge_pages;
 	struct list_head hugepage_freelists[MAX_NUMNODES];

@@ -227,8 +230,6 @@ struct hstate *size_to_hstate(unsigned l
 
 extern struct hstate hstates[HUGE_MAX_HSTATE];
 
-#define global_hstate (hstates[0])
-
 static inline struct hstate *hstate_inode(struct inode *i)
 {
 	struct hugetlbfs_sb_info *hsb;

Index: linux-2.6/arch/x86/mm/hugetlbpage.c
===================================================================
@@ -259,6 +259,7 @@ static unsigned long hugetlb_get_unmappe
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;

@@ -271,7 +272,7 @@ static unsigned long hugetlb_get_unmappe
 	}
 
 full_search:
-	addr = ALIGN(start_addr, HPAGE_SIZE);
+	addr = ALIGN(start_addr, huge_page_size(h));
 
 	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
 		/* At this point:  (!vma || addr < vma->vm_end). */

@@ -293,7 +294,7 @@ full_search:
 		}
 		if (addr + mm->cached_hole_size < vma->vm_start)
 		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+		addr = ALIGN(vma->vm_end, huge_page_size(h));
 	}
 }
 

@@ -301,6 +302,7 @@ static unsigned long hugetlb_get_unmappe
 		unsigned long addr0, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev_vma;
 	unsigned long base = mm->mmap_base, addr = addr0;

@@ -321,7 +323,7 @@ try_again:
 		goto fail;
 
 	/* either no address requested or cant fit in requested address hole */
-	addr = (mm->free_area_cache - len) & HPAGE_MASK;
+	addr = (mm->free_area_cache - len) & huge_page_mask(h);
 	do {
 		/*
 		 * Lookup failure means no vma is above this address,

@@ -352,7 +354,7 @@ try_again:
 		        largest_hole = vma->vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start - len) & HPAGE_MASK;
+		addr = (vma->vm_start - len) & huge_page_mask(h);
 	} while (len <= vma->vm_start);
 
 fail:

@@ -390,10 +392,11 @@ unsigned long
 hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
-	if (len & ~HPAGE_MASK)
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
 	if (len > TASK_SIZE)
 		return -ENOMEM;

@@ -405,7 +408,7 @@ hugetlb_get_unmapped_area(struct file *f
 	}
 
 	if (addr) {
-		addr = ALIGN(addr, HPAGE_SIZE);
+		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
 		    (!vma || addr + len <= vma->vm_start))