X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fhugetlb.c;h=51c9e2c0164068681b299b37f48840af59d5c79d;hb=c0d43990768b6ca83604ff4be80425b89d317e2f;hp=27fad5d9bcf648b27564465b35c3cd72969257fa;hpb=b45b5bd65f668a665db40d093e4e1fe563533608;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 27fad5d..51c9e2c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -22,11 +22,19 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, reserved_huge_pages;
+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;
+
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
@@ -39,19 +47,19 @@ static void clear_huge_page(struct page *page, unsigned long addr)
 	might_sleep();
 	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
 		cond_resched();
-		clear_user_highpage(page + i, addr);
+		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
 	}
 }
 
 static void copy_huge_page(struct page *dst, struct page *src,
-			   unsigned long addr)
+			   unsigned long addr, struct vm_area_struct *vma)
 {
 	int i;
 
 	might_sleep();
 	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
 		cond_resched();
-		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE);
+		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
 	}
 }
 
@@ -63,193 +71,422 @@ static void enqueue_huge_page(struct page *page)
 	free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page(void)
+{
+	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,
+					  struct page, lru);
+			list_del(&page->lru);
+			free_huge_pages--;
+			free_huge_pages_node[nid]--;
+			break;
+		}
+	}
+	return page;
+}
+
+static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 				unsigned long address)
 {
-	int nid = numa_node_id();
+	int nid;
 	struct page *page = NULL;
-	struct zonelist *zonelist = huge_zonelist(vma, address);
+	struct mempolicy *mpol;
+	struct zonelist *zonelist = huge_zonelist(vma, address,
+					htlb_alloc_mask, &mpol);
 	struct zone **z;
 
 	for (z = zonelist->zones; *z; z++) {
-		nid = (*z)->zone_pgdat->node_id;
-		if (cpuset_zone_allowed(*z, GFP_HIGHUSER) &&
-		    !list_empty(&hugepage_freelists[nid]))
+		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,
+					  struct page, lru);
+			list_del(&page->lru);
+			free_huge_pages--;
+			free_huge_pages_node[nid]--;
+			if (vma && vma->vm_flags & VM_MAYSHARE)
+				resv_huge_pages--;
 			break;
+		}
 	}
+	mpol_free(mpol);	/* unref if mpol !NULL */
+	return page;
+}
 
-	if (*z) {
-		page = list_entry(hugepage_freelists[nid].next,
-				  struct page, lru);
-		list_del(&page->lru);
-		free_huge_pages--;
-		free_huge_pages_node[nid]--;
+static void update_and_free_page(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++) {
+		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);
 	}
-	return page;
+	set_compound_page_dtor(page, NULL);
+	set_page_refcounted(page);
+	__free_pages(page, HUGETLB_PAGE_ORDER);
 }
 
-static int alloc_fresh_huge_page(void)
+static void free_huge_page(struct page *page)
+{
+	int nid = page_to_nid(page);
+	struct address_space *mapping;
+
+	mapping = (struct address_space *) page_private(page);
+	set_page_private(page, 0);
+	BUG_ON(page_count(page));
+	INIT_LIST_HEAD(&page->lru);
+
+	spin_lock(&hugetlb_lock);
+	if (surplus_huge_pages_node[nid]) {
+		update_and_free_page(page);
+		surplus_huge_pages--;
+		surplus_huge_pages_node[nid]--;
+	} else {
+		enqueue_huge_page(page);
+	}
+	spin_unlock(&hugetlb_lock);
+	if (mapping)
+		hugetlb_put_quota(mapping, 1);
+}
+
+/*
+ * Increment or decrement surplus_huge_pages.  Keep node-specific counters
+ * balanced by operating on them in a round-robin fashion.
+ * Returns 1 if an adjustment was made.
+ */
+static int adjust_pool_surplus(int delta)
+{
+	static int prev_nid;
+	int nid = prev_nid;
+	int ret = 0;
+
+	VM_BUG_ON(delta != -1 && delta != 1);
+	do {
+		nid = next_node(nid, node_online_map);
+		if (nid == MAX_NUMNODES)
+			nid = first_node(node_online_map);
+
+		/* To shrink on this node, there must be a surplus page */
+		if (delta < 0 && !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])
+			continue;
+
+		surplus_huge_pages += delta;
+		surplus_huge_pages_node[nid] += delta;
+		ret = 1;
+		break;
+	} while (nid != prev_nid);
+
+	prev_nid = nid;
+	return ret;
+}
+
+static struct page *alloc_fresh_huge_page_node(int nid)
 {
-	static int nid = 0;
 	struct page *page;
-	page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
-					HUGETLB_PAGE_ORDER);
-	nid = (nid + 1) % num_online_nodes();
+
+	page = alloc_pages_node(nid,
+		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
+		HUGETLB_PAGE_ORDER);
 	if (page) {
-		page[1].lru.next = (void *)free_huge_page;	/* dtor */
+		set_compound_page_dtor(page, free_huge_page);
 		spin_lock(&hugetlb_lock);
 		nr_huge_pages++;
-		nr_huge_pages_node[page_to_nid(page)]++;
+		nr_huge_pages_node[nid]++;
 		spin_unlock(&hugetlb_lock);
 		put_page(page); /* free it into the hugepage allocator */
-		return 1;
 	}
-	return 0;
+
+	return page;
 }
 
-void free_huge_page(struct page *page)
+static int alloc_fresh_huge_page(void)
 {
-	BUG_ON(page_count(page));
+	struct page *page;
+	int start_nid;
+	int next_nid;
+	int ret = 0;
 
-	INIT_LIST_HEAD(&page->lru);
+	start_nid = hugetlb_next_nid;
 
-	spin_lock(&hugetlb_lock);
-	enqueue_huge_page(page);
-	spin_unlock(&hugetlb_lock);
+	do {
+		page = alloc_fresh_huge_page_node(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(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);
+
+	return ret;
 }
 
-struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
+static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
+						unsigned long address)
 {
-	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct page *page;
-	int use_reserve = 0;
-	unsigned long idx;
+	unsigned int nid;
 
+	/*
+	 * Assume we will successfully allocate the surplus page to
+	 * prevent racing processes from causing the surplus to exceed
+	 * overcommit
+	 *
+	 * This however introduces a different race, where a process B
+	 * tries to grow the static hugepage pool while alloc_pages() is
+	 * called by process A. B will only examine the per-node
+	 * counters in determining if surplus huge pages can be
+	 * converted to normal huge pages in adjust_pool_surplus(). A
+	 * won't be able to increment the per-node counter, until the
+	 * lock is dropped by B, but B doesn't drop hugetlb_lock until
+	 * no more huge pages can be converted from surplus to normal
+	 * state (and doesn't try to convert again). Thus, we have a
+	 * case where a surplus huge page exists, the pool is grown, and
+	 * the surplus huge page still exists after, even though it
+	 * should just have been converted to a normal huge page. This
+	 * does not leak memory, though, as the hugepage will be freed
+	 * once it is out of use. It also does not allow the counters to
+	 * go out of whack in adjust_pool_surplus() as we don't modify
+	 * the node values until we've gotten the hugepage and only the
+	 * per-node value is checked there.
+	 */
 	spin_lock(&hugetlb_lock);
-
-	if (vma->vm_flags & VM_MAYSHARE) {
-
-		/* idx = radix tree index, i.e. offset into file in
-		 * HPAGE_SIZE units */
-		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
-			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
-
-		/* The hugetlbfs specific inode info stores the number
-		 * of "guaranteed available" (huge) pages.  That is,
-		 * the first 'prereserved_hpages' pages of the inode
-		 * are either already instantiated, or have been
-		 * pre-reserved (by hugetlb_reserve_for_inode()). Here
-		 * we're in the process of instantiating the page, so
-		 * we use this to determine whether to draw from the
-		 * pre-reserved pool or the truly free pool. */
-		if (idx < HUGETLBFS_I(inode)->prereserved_hpages)
-			use_reserve = 1;
-	}
-
-	if (!use_reserve) {
-		if (free_huge_pages <= reserved_huge_pages)
-			goto fail;
+	if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+		spin_unlock(&hugetlb_lock);
+		return NULL;
 	} else {
-		BUG_ON(reserved_huge_pages == 0);
-		reserved_huge_pages--;
+		nr_huge_pages++;
+		surplus_huge_pages++;
 	}
+	spin_unlock(&hugetlb_lock);
 
-	page = dequeue_huge_page(vma, addr);
-	if (!page)
-		goto fail;
+	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+					HUGETLB_PAGE_ORDER);
 
+	spin_lock(&hugetlb_lock);
+	if (page) {
+		/*
+		 * This page is now managed by the hugetlb allocator and has
+		 * no users -- drop the buddy allocator's reference.
+		 */
+		put_page_testzero(page);
+		VM_BUG_ON(page_count(page));
+		nid = page_to_nid(page);
+		set_compound_page_dtor(page, free_huge_page);
+		/*
+		 * We incremented the global counters already
+		 */
+		nr_huge_pages_node[nid]++;
+		surplus_huge_pages_node[nid]++;
+	} else {
+		nr_huge_pages--;
+		surplus_huge_pages--;
+	}
 	spin_unlock(&hugetlb_lock);
-	set_page_refcounted(page);
-	return page;
 
- fail:
-	WARN_ON(use_reserve); /* reserved allocations shouldn't fail */
-	spin_unlock(&hugetlb_lock);
-	return NULL;
+	return page;
 }
 
-/* hugetlb_extend_reservation()
- *
- * Ensure that at least 'atleast' hugepages are, and will remain,
- * available to instantiate the first 'atleast' pages of the given
- * inode.  If the inode doesn't already have this many pages reserved
- * or instantiated, set aside some hugepages in the reserved pool to
- * satisfy later faults (or fail now if there aren't enough, rather
- * than getting the SIGBUS later).
+/*
+ * Increase the hugetlb pool such that it can accomodate a reservation
+ * of size 'delta'.
  */
-int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info,
-			       unsigned long atleast)
+static int gather_surplus_pages(int delta)
 {
-	struct inode *inode = &info->vfs_inode;
-	unsigned long change_in_reserve = 0;
-	int ret = 0;
-
-	spin_lock(&hugetlb_lock);
-	read_lock_irq(&inode->i_mapping->tree_lock);
+	struct list_head surplus_list;
+	struct page *page, *tmp;
+	int ret, i;
+	int needed, allocated;
+
+	needed = (resv_huge_pages + delta) - free_huge_pages;
+	if (needed <= 0) {
+		resv_huge_pages += delta;
+		return 0;
+	}
 
-	if (info->prereserved_hpages >= atleast)
-		goto out;
+	allocated = 0;
+	INIT_LIST_HEAD(&surplus_list);
 
-	/* Because we always call this on shared mappings, none of the
-	 * pages beyond info->prereserved_hpages can have been
-	 * instantiated, so we need to reserve all of them now. */
-	change_in_reserve = atleast - info->prereserved_hpages;
+	ret = -ENOMEM;
+retry:
+	spin_unlock(&hugetlb_lock);
+	for (i = 0; i < needed; i++) {
+		page = alloc_buddy_huge_page(NULL, 0);
+		if (!page) {
+			/*
+			 * We were not able to allocate enough pages to
+			 * satisfy the entire reservation so we free what
+			 * we've allocated so far.
+			 */
+			spin_lock(&hugetlb_lock);
+			needed = 0;
+			goto free;
+		}
 
-	if ((reserved_huge_pages + change_in_reserve) > free_huge_pages) {
-		ret = -ENOMEM;
-		goto out;
+		list_add(&page->lru, &surplus_list);
 	}
+	allocated += needed;
 
-	reserved_huge_pages += change_in_reserve;
-	info->prereserved_hpages = atleast;
+	/*
+	 * After retaking hugetlb_lock, we need to recalculate 'needed'
+	 * because either resv_huge_pages or free_huge_pages may have changed.
+	 */
+	spin_lock(&hugetlb_lock);
+	needed = (resv_huge_pages + delta) - (free_huge_pages + allocated);
+	if (needed > 0)
+		goto retry;
 
- out:
-	read_unlock_irq(&inode->i_mapping->tree_lock);
-	spin_unlock(&hugetlb_lock);
+	/*
+	 * The surplus_list now contains _at_least_ the number of extra pages
+	 * needed to accomodate the reservation.  Add the appropriate number
+	 * of pages to the hugetlb pool and free the extras back to the buddy
+	 * allocator.  Commit the entire reservation here to prevent another
+	 * process from stealing the pages as they are added to the pool but
+	 * before they are reserved.
+	 */
+	needed += allocated;
+	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);
+		else {
+			/*
+			 * The page has a reference count of zero already, so
+			 * call free_huge_page directly instead of using
+			 * put_page.  This must be done with hugetlb_lock
+			 * unlocked which is safe because free_huge_page takes
+			 * hugetlb_lock before deciding how to free the page.
+			 */
+			spin_unlock(&hugetlb_lock);
+			free_huge_page(page);
+			spin_lock(&hugetlb_lock);
+		}
+	}
 
 	return ret;
 }
 
-/* hugetlb_truncate_reservation()
- *
- * This returns pages reserved for the given inode to the general free
- * hugepage pool.  If the inode has any pages prereserved, but not
- * instantiated, beyond offset (atmost << HPAGE_SIZE), then release
- * them.
+/*
+ * When releasing a hugetlb pool reservation, any surplus pages that were
+ * allocated to satisfy the reservation must be explicitly freed if they were
+ * never used.
  */
-void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info,
-				  unsigned long atmost)
+static void return_unused_surplus_pages(unsigned long unused_resv_pages)
 {
-	struct inode *inode = &info->vfs_inode;
-	struct address_space *mapping = inode->i_mapping;
-	unsigned long idx;
-	unsigned long change_in_reserve = 0;
+	static int nid = -1;
 	struct page *page;
+	unsigned long nr_pages;
 
-	spin_lock(&hugetlb_lock);
-	read_lock_irq(&inode->i_mapping->tree_lock);
+	/*
+	 * We want to release as many surplus pages as possible, spread
+	 * evenly across all nodes. Iterate across all nodes until we
+	 * can no longer free unreserved surplus pages. This occurs when
+	 * the nodes with surplus pages have no free pages.
+	 */
+	unsigned long remaining_iterations = num_online_nodes();
 
-	if (info->prereserved_hpages <= atmost)
-		goto out;
+	/* Uncommit the reservation */
+	resv_huge_pages -= unused_resv_pages;
 
-	/* Count pages which were reserved, but not instantiated, and
-	 * which we can now release. */
-	for (idx = atmost; idx < info->prereserved_hpages; idx++) {
-		page = radix_tree_lookup(&mapping->page_tree, idx);
-		if (!page)
-			/* Pages which are already instantiated can't
-			 * be unreserved (and in fact have already
-			 * been removed from the reserved pool) */
-			change_in_reserve++;
+	nr_pages = min(unused_resv_pages, 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])
+			continue;
+
+		if (!list_empty(&hugepage_freelists[nid])) {
+			page = list_entry(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]--;
+			nr_pages--;
+			remaining_iterations = num_online_nodes();
+		}
 	}
+}
 
-	BUG_ON(reserved_huge_pages < change_in_reserve);
-	reserved_huge_pages -= change_in_reserve;
-	info->prereserved_hpages = atmost;
 
- out:
-	read_unlock_irq(&inode->i_mapping->tree_lock);
+static struct page *alloc_huge_page_shared(struct vm_area_struct *vma,
+						unsigned long addr)
+{
+	struct page *page;
+
+	spin_lock(&hugetlb_lock);
+	page = dequeue_huge_page_vma(vma, addr);
 	spin_unlock(&hugetlb_lock);
+	return page ? page : ERR_PTR(-VM_FAULT_OOM);
+}
+
+static struct page *alloc_huge_page_private(struct vm_area_struct *vma,
+						unsigned long addr)
+{
+	struct page *page = NULL;
+
+	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)
+		page = dequeue_huge_page_vma(vma, addr);
+	spin_unlock(&hugetlb_lock);
+	if (!page) {
+		page = alloc_buddy_huge_page(vma, addr);
+		if (!page) {
+			hugetlb_put_quota(vma->vm_file->f_mapping, 1);
+			return ERR_PTR(-VM_FAULT_OOM);
+		}
+	}
+	return page;
+}
+
+static struct page *alloc_huge_page(struct vm_area_struct *vma,
+				    unsigned long addr)
+{
+	struct page *page;
+	struct address_space *mapping = vma->vm_file->f_mapping;
+
+	if (vma->vm_flags & VM_MAYSHARE)
+		page = alloc_huge_page_shared(vma, addr);
+	else
+		page = alloc_huge_page_private(vma, addr);
+
+	if (!IS_ERR(page)) {
+		set_page_refcounted(page);
+		set_page_private(page, (unsigned long) mapping);
+	}
+	return page;
 }
 
 static int __init hugetlb_init(void)
@@ -262,6 +499,8 @@ static int __init hugetlb_init(void)
 	for (i = 0; i < MAX_NUMNODES; ++i)
 		INIT_LIST_HEAD(&hugepage_freelists[i]);
 
+	hugetlb_next_nid = first_node(node_online_map);
+
 	for (i = 0; i < max_huge_pages; ++i) {
 		if (!alloc_fresh_huge_page())
 			break;
@@ -280,38 +519,34 @@ static int __init hugetlb_setup(char *s)
 }
 __setup("hugepages=", hugetlb_setup);
 
-#ifdef CONFIG_SYSCTL
-static void update_and_free_page(struct page *page)
+static unsigned int cpuset_mems_nr(unsigned int *array)
 {
-	int i;
-	nr_huge_pages--;
-	nr_huge_pages_node[page_zone(page)->zone_pgdat->node_id]--;
-	for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); 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);
-	}
-	page[1].lru.next = NULL;
-	set_page_refcounted(page);
-	__free_pages(page, HUGETLB_PAGE_ORDER);
+	int node;
+	unsigned int nr = 0;
+
+	for_each_node_mask(node, cpuset_current_mems_allowed)
+		nr += array[node];
+
+	return nr;
 }
 
+#ifdef CONFIG_SYSCTL
 #ifdef CONFIG_HIGHMEM
 static void try_to_free_low(unsigned long count)
 {
-	int i, nid;
+	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)
+				return;
 			if (PageHighMem(page))
 				continue;
 			list_del(&page->lru);
 			update_and_free_page(page);
-			nid = page_zone(page)->zone_pgdat->node_id;
 			free_huge_pages--;
-			free_huge_pages_node[nid]--;
-			if (count >= nr_huge_pages)
-				return;
+			free_huge_pages_node[page_to_nid(page)]--;
 		}
 	}
 }
@@ -321,25 +556,75 @@ static inline void try_to_free_low(unsigned long count)
 }
 #endif
 
+#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)
 static unsigned long set_max_huge_pages(unsigned long count)
 {
-	while (count > nr_huge_pages) {
-		if (!alloc_fresh_huge_page())
-			return nr_huge_pages;
-	}
-	if (count >= nr_huge_pages)
-		return nr_huge_pages;
+	unsigned long min_count, ret;
 
+	/*
+	 * Increase the pool size
+	 * First take pages out of surplus state.  Then make up the
+	 * remaining difference by allocating fresh huge pages.
+	 *
+	 * We might race with alloc_buddy_huge_page() here and be unable
+	 * to convert a surplus huge page to a normal huge page. That is
+	 * not critical, though, it just means the overall size of the
+	 * pool might be one hugepage larger than it needs to be, but
+	 * within all the constraints specified by the sysctls.
+	 */
 	spin_lock(&hugetlb_lock);
-	try_to_free_low(count);
-	while (count < nr_huge_pages) {
-		struct page *page = dequeue_huge_page(NULL, 0);
+	while (surplus_huge_pages && count > persistent_huge_pages) {
+		if (!adjust_pool_surplus(-1))
+			break;
+	}
+
+	while (count > persistent_huge_pages) {
+		int ret;
+		/*
+		 * 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();
+		spin_lock(&hugetlb_lock);
+		if (!ret)
+			goto out;
+
+	}
+
+	/*
+	 * Decrease the pool size
+	 * First return free pages to the buddy allocator (being careful
+	 * to keep enough around to satisfy reservations).  Then place
+	 * pages into surplus state as needed so the pool will shrink
+	 * to the desired size as pages become free.
+	 *
+	 * By placing pages into the surplus state independent of the
+	 * overcommit value, we are allowing the surplus pool size to
+	 * exceed overcommit. There are few sane options here. Since
+	 * alloc_buddy_huge_page() is checking the global counter,
+	 * though, we'll note that we're not allowed to exceed surplus
+	 * and won't grow the pool anywhere else. Not until one of the
+	 * sysctls are changed, or the surplus pages go out of use.
+	 */
+	min_count = resv_huge_pages + nr_huge_pages - 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();
 		if (!page)
 			break;
 		update_and_free_page(page);
 	}
+	while (count < persistent_huge_pages) {
+		if (!adjust_pool_surplus(1))
+			break;
+	}
+out:
+	ret = persistent_huge_pages;
 	spin_unlock(&hugetlb_lock);
-	return nr_huge_pages;
+	return ret;
 }
 
 int hugetlb_sysctl_handler(struct ctl_table *table, int write,
@@ -350,6 +635,30 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 	max_huge_pages = set_max_huge_pages(max_huge_pages);
 	return 0;
 }
+
+int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
+			struct file *file, void __user *buffer,
+			size_t *length, loff_t *ppos)
+{
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (hugepages_treat_as_movable)
+		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
+	else
+		htlb_alloc_mask = GFP_HIGHUSER;
+	return 0;
+}
+
+int hugetlb_overcommit_handler(struct ctl_table *table, int write,
+			struct file *file, void __user *buffer,
+			size_t *length, loff_t *ppos)
+{
+	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+	spin_lock(&hugetlb_lock);
+	nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
+	spin_unlock(&hugetlb_lock);
+	return 0;
+}
+
 #endif /* CONFIG_SYSCTL */
 
 int hugetlb_report_meminfo(char *buf)
@@ -357,11 +666,13 @@ int hugetlb_report_meminfo(char *buf)
 	return sprintf(buf,
 			"HugePages_Total: %5lu\n"
 			"HugePages_Free:  %5lu\n"
-		        "HugePages_Rsvd:  %5lu\n"
+			"HugePages_Rsvd:  %5lu\n"
+			"HugePages_Surp:  %5lu\n"
 			"Hugepagesize:    %5lu kB\n",
 			nr_huge_pages,
 			free_huge_pages,
-		        reserved_huge_pages,
+			resv_huge_pages,
+			surplus_huge_pages,
 			HPAGE_SIZE/1024);
 }
 
@@ -369,9 +680,11 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 {
 	return sprintf(buf,
 		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %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, free_huge_pages_node[nid],
+		nid, surplus_huge_pages_node[nid]);
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
@@ -386,15 +699,14 @@ unsigned long hugetlb_total_pages(void)
  * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get
  * this far.
  */
-static struct page *hugetlb_nopage(struct vm_area_struct *vma,
-				unsigned long address, int *unused)
+static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	BUG();
-	return NULL;
+	return 0;
 }
 
 struct vm_operations_struct hugetlb_vm_ops = {
-	.nopage = hugetlb_nopage,
+	.fault = hugetlb_vm_op_fault,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
@@ -420,9 +732,9 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 	pte_t entry;
 
 	entry = pte_mkwrite(pte_mkdirty(*ptep));
-	ptep_set_access_flags(vma, address, ptep, entry, 1);
-	update_mmu_cache(vma, address, entry);
-	lazy_mmu_prot_update(entry);
+	if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+		update_mmu_cache(vma, address, entry);
+	}
 }
 
 
@@ -443,6 +755,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		dst_pte = huge_pte_alloc(dst, addr);
 		if (!dst_pte)
 			goto nomem;
+
+		/* If the pagetables are shared don't copy or take references */
+		if (dst_pte == src_pte)
+			continue;
+
 		spin_lock(&dst->page_table_lock);
 		spin_lock(&src->page_table_lock);
 		if (!pte_none(*src_pte)) {
@@ -451,7 +768,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = *src_pte;
 			ptepage = pte_page(entry);
 			get_page(ptepage);
-			add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
@@ -463,40 +779,68 @@ nomem:
 	return -ENOMEM;
 }
 
-void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-			  unsigned long end)
+void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
 	struct page *page;
+	struct page *tmp;
+	/*
+	 * A page gathering list, protected by per file i_mmap_lock. The
+	 * lock is used to avoid list corruption from multiple unmapping
+	 * of the same page since we are using page->lru.
+	 */
+	LIST_HEAD(page_list);
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~HPAGE_MASK);
 	BUG_ON(end & ~HPAGE_MASK);
 
 	spin_lock(&mm->page_table_lock);
-
-	/* Update high watermark before we lower rss */
-	update_hiwater_rss(mm);
-
 	for (address = start; address < end; address += HPAGE_SIZE) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		if (huge_pmd_unshare(mm, &address, ptep))
+			continue;
+
 		pte = huge_ptep_get_and_clear(mm, address, ptep);
 		if (pte_none(pte))
 			continue;
 
 		page = pte_page(pte);
-		put_page(page);
-		add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
+		if (pte_dirty(pte))
+			set_page_dirty(page);
+		list_add(&page->lru, &page_list);
 	}
-
 	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
+	list_for_each_entry_safe(page, tmp, &page_list, lru) {
+		list_del(&page->lru);
+		put_page(page);
+	}
+}
+
+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);
+	}
 }
 
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -512,19 +856,20 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	avoidcopy = (page_count(old_page) == 1);
 	if (avoidcopy) {
 		set_huge_ptep_writable(vma, address, ptep);
-		return VM_FAULT_MINOR;
+		return 0;
 	}
 
 	page_cache_get(old_page);
 	new_page = alloc_huge_page(vma, address);
 
-	if (!new_page) {
+	if (IS_ERR(new_page)) {
 		page_cache_release(old_page);
-		return VM_FAULT_OOM;
+		return -PTR_ERR(new_page);
 	}
 
 	spin_unlock(&mm->page_table_lock);
-	copy_huge_page(new_page, old_page, address);
+	copy_huge_page(new_page, old_page, address, vma);
+	__SetPageUptodate(new_page);
 	spin_lock(&mm->page_table_lock);
 
 	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
@@ -537,10 +882,10 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	page_cache_release(new_page);
 	page_cache_release(old_page);
-	return VM_FAULT_MINOR;
+	return 0;
 }
 
-int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, int write_access)
 {
 	int ret = VM_FAULT_SIGBUS;
@@ -561,27 +906,32 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
-		if (hugetlb_get_quota(mapping))
+		size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+		if (idx >= size)
 			goto out;
 		page = alloc_huge_page(vma, address);
-		if (!page) {
-			hugetlb_put_quota(mapping);
-			ret = VM_FAULT_OOM;
+		if (IS_ERR(page)) {
+			ret = -PTR_ERR(page);
 			goto out;
 		}
 		clear_huge_page(page, address);
+		__SetPageUptodate(page);
 
 		if (vma->vm_flags & VM_SHARED) {
 			int err;
+			struct inode *inode = mapping->host;
 
 			err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
 			if (err) {
 				put_page(page);
-				hugetlb_put_quota(mapping);
 				if (err == -EEXIST)
 					goto retry;
 				goto out;
 			}
+
+			spin_lock(&inode->i_lock);
+			inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+			spin_unlock(&inode->i_lock);
 		} else
 			lock_page(page);
 	}
@@ -591,11 +941,10 @@ retry:
 	if (idx >= size)
 		goto backout;
 
-	ret = VM_FAULT_MINOR;
+	ret = 0;
 	if (!pte_none(*ptep))
 		goto backout;
 
-	add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
@@ -612,7 +961,6 @@ out:
 
 backout:
 	spin_unlock(&mm->page_table_lock);
-	hugetlb_put_quota(mapping);
 	unlock_page(page);
 	put_page(page);
 	goto out;
@@ -643,7 +991,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		return ret;
 	}
 
-	ret = VM_FAULT_MINOR;
+	ret = 0;
 
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
@@ -658,12 +1006,13 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 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)
+			unsigned long *position, int *length, int i,
+			int write)
 {
-	unsigned long vpfn, vaddr = *position;
+	unsigned long pfn_offset;
+	unsigned long vaddr = *position;
 	int remainder = *length;
 
-	vpfn = vaddr/PAGE_SIZE;
 	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
@@ -676,13 +1025,13 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
 
-		if (!pte || pte_none(*pte)) {
+		if (!pte || pte_none(*pte) || (write && !pte_write(*pte))) {
 			int ret;
 
 			spin_unlock(&mm->page_table_lock);
-			ret = hugetlb_fault(mm, vma, vaddr, 0);
+			ret = hugetlb_fault(mm, vma, vaddr, write);
 			spin_lock(&mm->page_table_lock);
-			if (ret == VM_FAULT_MINOR)
+			if (!(ret & VM_FAULT_ERROR))
 				continue;
 
 			remainder = 0;
@@ -691,19 +1040,29 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
+		pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+		page = pte_page(*pte);
+same_page:
 		if (pages) {
-			page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
 			get_page(page);
-			pages[i] = page;
+			pages[i] = page + pfn_offset;
 		}
 
 		if (vmas)
 			vmas[i] = vma;
 
 		vaddr += PAGE_SIZE;
-		++vpfn;
+		++pfn_offset;
 		--remainder;
 		++i;
+		if (vaddr < vma->vm_end && remainder &&
+				pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+			/*
+			 * We use pfn_offset to avoid touching the pageframes
+			 * of this compound page.
+			 */
+			goto same_page;
+		}
 	}
 	spin_unlock(&mm->page_table_lock);
 	*length = remainder;
@@ -723,20 +1082,215 @@ void hugetlb_change_protection(struct vm_area_struct *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) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		if (huge_pmd_unshare(mm, &address, ptep))
+			continue;
 		if (!pte_none(*ptep)) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(pte_modify(pte, newprot));
 			set_huge_pte_at(mm, address, ptep, pte);
-			lazy_mmu_prot_update(pte);
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
+	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 
 	flush_tlb_range(vma, start, end);
 }
 
+struct file_region {
+	struct list_head link;
+	long from;
+	long to;
+};
+
+static long region_add(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg, *trg;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+
+	/* Check for and consume any regions we now overlap with. */
+	nrg = rg;
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			break;
+
+		/* If this area reaches higher then extend our area to
+		 * include it completely.  If this is not the first area
+		 * which we intend to reuse, free it. */
+		if (rg->to > t)
+			t = rg->to;
+		if (rg != nrg) {
+			list_del(&rg->link);
+			kfree(rg);
+		}
+	}
+	nrg->from = f;
+	nrg->to = t;
+	return 0;
+}
+
+static long region_chg(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg;
+	long chg = 0;
+
+	/* Locate the region we are before or in. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* If we are below the current region then a new region is required.
+	 * Subtle, allocate a new region at the position but make it zero
+	 * size such that we can guarantee to record the reservation. */
+	if (&rg->link == head || t < rg->from) {
+		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+		if (!nrg)
+			return -ENOMEM;
+		nrg->from = f;
+		nrg->to   = f;
+		INIT_LIST_HEAD(&nrg->link);
+		list_add(&nrg->link, rg->link.prev);
+
+		return t - f;
+	}
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+	chg = t - f;
+
+	/* Check for and consume any regions we now overlap with. */
+	list_for_each_entry(rg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			return chg;
+
+		/* We overlap with this area, if it extends futher than
+		 * us then we must extend ourselves.  Account for its
+		 * existing reservation. */
+		if (rg->to > t) {
+			chg += rg->to - t;
+			t = rg->to;
+		}
+		chg -= rg->to - rg->from;
+	}
+	return chg;
+}
+
+static long region_truncate(struct list_head *head, long end)
+{
+	struct file_region *rg, *trg;
+	long chg = 0;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (end <= rg->to)
+			break;
+	if (&rg->link == head)
+		return 0;
+
+	/* If we are in the middle of a region then adjust it. */
+	if (end > rg->from) {
+		chg = rg->to - end;
+		rg->to = end;
+		rg = list_entry(rg->link.next, typeof(*rg), link);
+	}
+
+	/* Drop any remaining regions. */
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		chg += rg->to - rg->from;
+		list_del(&rg->link);
+		kfree(rg);
+	}
+	return chg;
+}
+
+static int hugetlb_acct_memory(long delta)
+{
+	int ret = -ENOMEM;
+
+	spin_lock(&hugetlb_lock);
+	/*
+	 * When cpuset is configured, it breaks the strict hugetlb page
+	 * reservation as the accounting is done on a global variable. Such
+	 * reservation is completely rubbish in the presence of cpuset because
+	 * the reservation is not checked against page availability for the
+	 * current cpuset. Application can still potentially OOM'ed by kernel
+	 * with lack of free htlb page in cpuset that the task is in.
+	 * Attempt to enforce strict accounting with cpuset is almost
+	 * impossible (or too ugly) because cpuset is too fluid that
+	 * task or memory node can be dynamically moved between cpusets.
+	 *
+	 * The change of semantics for shared hugetlb mapping with cpuset is
+	 * undesirable. However, in order to preserve some of the semantics,
+	 * we fall back to check against current free page availability as
+	 * a best attempt and hopefully to minimize the impact of changing
+	 * semantics that cpuset has.
+	 */
+	if (delta > 0) {
+		if (gather_surplus_pages(delta) < 0)
+			goto out;
+
+		if (delta > cpuset_mems_nr(free_huge_pages_node)) {
+			return_unused_surplus_pages(delta);
+			goto out;
+		}
+	}
+
+	ret = 0;
+	if (delta < 0)
+		return_unused_surplus_pages((unsigned long) -delta);
+
+out:
+	spin_unlock(&hugetlb_lock);
+	return ret;
+}
+
+int hugetlb_reserve_pages(struct inode *inode, long from, long to)
+{
+	long ret, chg;
+
+	chg = region_chg(&inode->i_mapping->private_list, from, to);
+	if (chg < 0)
+		return chg;
+
+	if (hugetlb_get_quota(inode->i_mapping, chg))
+		return -ENOSPC;
+	ret = hugetlb_acct_memory(chg);
+	if (ret < 0) {
+		hugetlb_put_quota(inode->i_mapping, chg);
+		return ret;
+	}
+	region_add(&inode->i_mapping->private_list, from, to);
+	return 0;
+}
+
+void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+{
+	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+
+	spin_lock(&inode->i_lock);
+	inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+	spin_unlock(&inode->i_lock);
+
+	hugetlb_put_quota(inode->i_mapping, (chg - freed));
+	hugetlb_acct_memory(-(chg - freed));
+}