Dynamic huge page pool resizing

index de4cf45..1dfeafa 100644
@@ -428,6 +428,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			continue;
 
 		page = pte_page(pte);
+		mm->locked_vm -= HPAGE_SIZE >> PAGE_SHIFT;
 		if (pte_dirty(pte))
 			set_page_dirty(page);
 		list_add(&page->lru, &page_list);

@@ -561,6 +562,16 @@ retry:
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
 
+	/*
+ 	 * Account for huge pages as locked memory.
+ 	 * The locked limits are not enforced at mmap time because hugetlbfs
+ 	 * behaves differently than normal locked memory:  1) The pages are
+ 	 * not pinned immediately, and 2) The pages come from a pre-configured
+ 	 * pool of memory to which the administrator has separately arranged
+ 	 * access.
+ 	 */
+	mm->locked_vm += HPAGE_SIZE >> PAGE_SHIFT;
+
 	if (write_access && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
 		ret = hugetlb_cow(mm, vma, address, ptep, new_pte);

index 1dfeafa..50195a2 100644
@@ -90,6 +90,21 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 	return page;
 }
 
+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);
+	}
+	set_compound_page_dtor(page, NULL);
+	set_page_refcounted(page);
+	__free_pages(page, HUGETLB_PAGE_ORDER);
+}
+
 static void free_huge_page(struct page *page)
 {
 	BUG_ON(page_count(page));

@@ -199,21 +214,6 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 }
 
 #ifdef CONFIG_SYSCTL
-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);
-	}
-	set_compound_page_dtor(page, NULL);
-	set_page_refcounted(page);
-	__free_pages(page, HUGETLB_PAGE_ORDER);
-}
-
 #ifdef CONFIG_HIGHMEM
 static void try_to_free_low(unsigned long count)
 {

index 50195a2..ec5207e 100644
@@ -27,6 +27,7 @@ unsigned long max_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;
 

@@ -107,12 +108,18 @@ static void update_and_free_page(struct page *page)
 
 static void free_huge_page(struct page *page)
 {
-	BUG_ON(page_count(page));
+	int nid = page_to_nid(page);
 
+	BUG_ON(page_count(page));
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
-	enqueue_huge_page(page);
+	if (surplus_huge_pages_node[nid]) {
+		update_and_free_page(page);
+		surplus_huge_pages_node[nid]--;
+	} else {
+		enqueue_huge_page(page);
+	}
 	spin_unlock(&hugetlb_lock);
 }
 

@@ -148,10 +155,57 @@ static int alloc_fresh_huge_page(void)
 	return 0;
 }
 
+/*
+ * Returns 1 if a process remains within lock limits after locking
+ * hpage_delta huge pages. It is expected that mmap_sem is held
+ * when calling this function, otherwise the locked_vm counter may
+ * change unexpectedly
+ */
+static int within_locked_vm_limits(long hpage_delta)
+{
+	unsigned long locked_pages, locked_pages_limit;
+
+	/* Check locked page limits */
+	locked_pages = current->mm->locked_vm;
+	locked_pages += hpage_delta * (HPAGE_SIZE >> PAGE_SHIFT);
+	locked_pages_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+	locked_pages_limit >>= PAGE_SHIFT;
+
+	/* Return 0 if we would exceed locked_vm limits */
+	if (locked_pages > locked_pages_limit)
+		return 0;
+
+	/* Nice, we're within limits */
+	return 1;
+}
+
+static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
+						unsigned long address)
+{
+	struct page *page;
+
+	/* Check we remain within limits if 1 huge page is allocated */
+	if (!within_locked_vm_limits(1))
+		return NULL;
+
+	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
+					HUGETLB_PAGE_ORDER);
+	if (page) {
+		set_compound_page_dtor(page, free_huge_page);
+		spin_lock(&hugetlb_lock);
+		nr_huge_pages++;
+		nr_huge_pages_node[page_to_nid(page)]++;
+		surplus_huge_pages_node[page_to_nid(page)]++;
+		spin_unlock(&hugetlb_lock);
+	}
+
+	return page;
+}
+
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr)
 {
-	struct page *page;
+	struct page *page = NULL;
 
 	spin_lock(&hugetlb_lock);
 	if (vma->vm_flags & VM_MAYSHARE)

@@ -171,7 +225,16 @@ fail:
 	if (vma->vm_flags & VM_MAYSHARE)
 		resv_huge_pages++;
 	spin_unlock(&hugetlb_lock);
-	return NULL;
+
+	/*
+	 * Private mappings do not use reserved huge pages so the allocation
+	 * may have failed due to an undersized hugetlb pool.  Try to grab a
+	 * surplus huge page from the buddy allocator.
+	 */
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		page = alloc_buddy_huge_page(vma, addr);
+
+	return page;
 }
 
 static int __init hugetlb_init(void)

index ec5207e..0cedcd0 100644
@@ -28,6 +28,7 @@ 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 unsigned long unused_surplus_pages;
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 

@@ -85,6 +86,10 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 			list_del(&page->lru);
 			free_huge_pages--;
 			free_huge_pages_node[nid]--;
+			if (vma && vma->vm_flags & VM_MAYSHARE) {
+				resv_huge_pages--;
+				unused_surplus_pages--;
+			}
 			break;
 		}
 	}

@@ -202,15 +207,120 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 	return page;
 }
 
+/*
+ * Increase the hugetlb pool such that it can accomodate a reservation
+ * of size 'delta'.
+ */
+static int gather_surplus_pages(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;
+	if (!needed)
+		return 0;
+
+	allocated = 0;
+	INIT_LIST_HEAD(&surplus_list);
+
+	ret = -ENOMEM;
+retry:
+	spin_unlock(&hugetlb_lock);
+	for (i = 0; i < needed; i++) {
+		page = alloc_buddy_huge_page(NULL, 0);
+		if (!page) {
+			/*
+			 * We were not able to allocate enough pages to
+			 * satisfy the entire reservation so we free what
+			 * we've allocated so far.
+			 */
+			spin_lock(&hugetlb_lock);
+			needed = 0;
+			goto free;
+		}
+
+		list_add(&page->lru, &surplus_list);
+	}
+	allocated += needed;
+
+	/*
+	 * After retaking hugetlb_lock, we need to recalculate 'needed'
+	 * because either resv_huge_pages or free_huge_pages may have changed.
+	 */
+	spin_lock(&hugetlb_lock);
+	needed = (resv_huge_pages + delta) - (free_huge_pages + allocated);
+	if (needed > 0)
+		goto retry;
+
+	/*
+	 * The surplus_list now contains _at_least_ the number of extra pages
+	 * needed to accomodate the reservation.  Add the appropriate number
+	 * of pages to the hugetlb pool and free the extras back to the buddy
+	 * allocator.
+	 *
+	 * Those pages that get added to the pool may never be allocated and
+	 * subsequently freed so keep track of them in unused_surplus_pages
+	 * so they can be freed again when a reservation is released.
+	 */
+	needed += allocated;
+	unused_surplus_pages += needed;
+	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
+			update_and_free_page(page);
+	}
+
+	return ret;
+}
+
+/*
+ * When releasing a reservation, free all unused, surplus huge pages that are
+ * no longer reserved.
+ */
+void return_unused_surplus_pages(void)
+{
+	static int nid = -1;
+	int delta;
+	struct page *page;
+
+	delta = unused_surplus_pages - resv_huge_pages;
+
+	while (delta) {
+		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_node[nid]--;
+			unused_surplus_pages--;
+			delta--;
+		}
+	}
+}
+
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr)
 {
 	struct page *page = NULL;
+	int use_reserved_page = vma->vm_flags & VM_MAYSHARE;
 
 	spin_lock(&hugetlb_lock);
-	if (vma->vm_flags & VM_MAYSHARE)
-		resv_huge_pages--;
-	else if (free_huge_pages <= resv_huge_pages)
+	if (!use_reserved_page && (free_huge_pages <= resv_huge_pages))
 		goto fail;
 
 	page = dequeue_huge_page(vma, addr);

@@ -222,8 +332,6 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	return page;
 
 fail:
-	if (vma->vm_flags & VM_MAYSHARE)
-		resv_huge_pages++;
 	spin_unlock(&hugetlb_lock);
 
 	/*

@@ -231,7 +339,7 @@ fail:
 	 * may have failed due to an undersized hugetlb pool.  Try to grab a
 	 * surplus huge page from the buddy allocator.
 	 */
-	if (!(vma->vm_flags & VM_MAYSHARE))
+	if (!use_reserved_page)
 		page = alloc_buddy_huge_page(vma, addr);
 
 	return page;

@@ -915,21 +1023,6 @@ static int hugetlb_acct_memory(long delta)
 	int ret = -ENOMEM;
 
 	spin_lock(&hugetlb_lock);
-	if ((delta + resv_huge_pages) <= free_huge_pages) {
-		resv_huge_pages += delta;
-		ret = 0;
-	}
-	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;
 	/*
 	 * When cpuset is configured, it breaks the strict hugetlb page
 	 * reservation as the accounting is done on a global variable. Such

@@ -947,8 +1040,30 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to)
 	 * a best attempt and hopefully to minimize the impact of changing
 	 * semantics that cpuset has.
 	 */
-	if (chg > cpuset_mems_nr(free_huge_pages_node))
-		return -ENOMEM;
+	if (delta > 0) {
+		if (gather_surplus_pages(delta) < 0)
+			goto out;
+
+		if (delta > cpuset_mems_nr(free_huge_pages_node))
+			goto out;
+	}
+
+	ret = 0;
+	resv_huge_pages += delta;
+	if (delta <= 0)
+		return_unused_surplus_pages();
+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;
 
 	ret = hugetlb_acct_memory(chg);
 	if (ret < 0)

index e6a71c8..cec45db 100644
@@ -33,6 +33,7 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 
 extern unsigned long max_huge_pages;
 extern unsigned long hugepages_treat_as_movable;
+extern int hugetlb_dynamic_pool;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;
 

index 8bdb8c0..fd60a5e 100644
@@ -879,6 +879,14 @@ static ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &hugetlb_treat_movable_handler,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hugetlb_dynamic_pool",
+		.data		= &hugetlb_dynamic_pool,
+		.maxlen		= sizeof(hugetlb_dynamic_pool),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #endif
 	{
 		.ctl_name	= VM_LOWMEM_RESERVE_RATIO,

index 0cedcd0..caef721 100644
@@ -31,6 +31,7 @@ static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 static unsigned long unused_surplus_pages;
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
+int hugetlb_dynamic_pool;
 
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages

@@ -189,6 +190,10 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
 {
 	struct page *page;
 
+	/* Check if the dynamic pool is enabled */
+	if (!hugetlb_dynamic_pool)
+		return NULL;
+
 	/* Check we remain within limits if 1 huge page is allocated */
 	if (!within_locked_vm_limits(1))
 		return NULL;